Henan University of Technology

About: Henan University of Technology is a education organization based out in Zhengzhou, China. It is known for research contribution in the topics: Catalysis & Starch. The organization has 7648 authors who have published 6503 publications receiving 73067 citations. The organization is also known as: Hénán Gōngyè Dàxué.

An Optimal SVM-Based Text Classification Algorithm

Abstract: The goal of a text classification system is to determine whether a given document belongs to which of the predefined categories. An optimal SVM algorithm for text classification via multiple optimal strategies is proposed in this paper. The experimental results indicate that the proposed optimal classification algorithm yields much better performance than other conventional algorithms.

Generating project risk response strategies based on CBR

Abstract: A new pragmatic CBR-based method for generating project risk response strategies is proposed.The most similar historical cases can be retrieved using the method.The inapplicable strategies are revised to support the generation of the candidate strategy set.The desirable project risk response strategies are generated through the expert's evaluations.Case problem on risk response of the subway project is solved based on this study. Risk response is an important work in project risk management (PRM). To generate project risk response strategies, retrieving and reusing information and knowledge of the similar historical cases is important, while research concerning this issue is still relatively scarce. Taking the risk response of the subway project in S city, China as a case problem, this paper proposes a pragmatic method for generating project risk response strategies based on the case-based reasoning (CBR). The procedure of the method include the five parts: first, representing the target case and the historical cases; second, retrieving the available historical cases by judging whether the risks involved in each historical case cover or are the same as those in the target case; third, retrieving the similar historical cases by measuring the similarity between each available historical case and the target case; fourth, revising the inapplicable risk response strategies involved in the similar historical cases by analyzing the response relation between each strategy and each risk of the current project; and generating the desirable risk response strategies by evaluating each candidate risk response strategy set. To illustrate the use of the proposed method, an empirical analysis of generating the risk response strategies for the subway station project is given. The proposed method can support project managers to make the better decision in PRM.